Evaluation - task1-intertass-ES
1899 tweets in qrel, 1899 tweets in run.

Accuracy: 0.591

Confusion matrix
Real	Pred.	#
N	N	593
N	P	78
N	NONE	80
N	NEU	16
NEU	NONE	51
NEU	N	107
NEU	P	53
NEU	NEU	5
NONE	NONE	120
NONE	P	58
NONE	N	91
NONE	NEU	5
P	NONE	89
P	N	139
P	P	405
P	NEU	9

Category evaluation
Cat	P	R	F1
N	0.638	0.773	0.699
NEU	0.143	0.023	0.040
NONE	0.353	0.438	0.391
P	0.682	0.631	0.655

Macro-Precision: 0.454
Macro-Recall: 0.466
Macro-F1: 0.460